How Effectively Agents Write D

[Peter Alexander]

On Friday, 6 November 2026 at 17:07:21 UTC, Paolo Invernizzi 
wrote:
> On Friday, 6 November 2026 at 15:23:33 UTC, Peter Alexander 
> wrote:
>
>> Keen to hear any and all feedback. Also interesting in what 
>> other ideas people have for how to measure D for agents.
>
> Perhaps this is disrespectful - if so, I apologize in advance - 
> but here is our experience; *claude-code* itself provides the 
> answer (based on its own memories and rules).

Not at all! Claude is often the best to analyse its own 
experiences, so appreciate taking the time to run this. Great to 
see it confirming a bunch of the findings, sharing the 
workarounds, and the additional things that my benchmark missed.